TSGen, an automated pipeline for generating high-quality, structured TSGs from historical incident reports using large language models (LLMs), consists of filtering and classifying incident data into diagnostically relevant categories and distilling core incidents to ensure diversity and generalizability.
Yi Xiao, Hongyu Zhang, Dr. I. I. Genkin et al.· SIGSOFT FSE Companion· 0 citations
DepRepair is proposed, a single-call LLM approach that grounds repair in structured upstream evidence through three components: an evidence filter that distills relevant upstream changes, a usage locator that identifies affected consumer sites, and a subcategory-aware guide that tailors repairs to the breaking-change t...
Shenghao Yang, Bo Lu, Yao Liu et al.· arXiv.org· 0 citations
Large language model (LLM) agents are increasingly used for multi-step, stateful tool-use tasks, yet production reliability remains limited. Unlike static software repair, agent repair must recover dynamic trajectories whose early decisions can propagate into later errors and external state changes. Existing automatic...
Chenyu Zhao, Shenglin Zhang, Wenwei Gu et al.· 2 citations
This work presents Change2Task, a system grounded in repository history that converts merged pull requests into verified tasks on healthy modern revisions of the same repository, and provides executable data for coding agent training and evaluation while reducing repeated environment setup, storage, and task constructi...
